Which security tools exist for onchain agents?

PulseFeed checks an x402 endpoint before an agent pays it (liveness, a 0-100 score, receiver and price flags) and tracks changes to MCP servers and npm packages. Ships a guard SDK, an MCP server, and Vercel AI SDK and LangChain tools.

Dependency and package analysis from Socket, with a CLI and an MCP server that returns package scores to an AI assistant.

Open-source zero-knowledge identity protocol (passport-based proof of personhood) used to gate agent access to onchain services.

MIT-licensed runtime guard for AI coding agents: hook-level action blocking, a 24-rule skill scanner, and a per-skill trust registry.

A registry of AI agent skills that applies automated source-code scanning and assigns security grades before installation.

MCP server from SlowMist exposing MistTrack address risk scoring and fund-flow tracing to AI agents.

Privacy infrastructure that gives MCP-compatible agents private wallets, encrypted messaging, and confidential smart contracts using Garbled Circuits.

Open-source privacy SDK that adds unlinkable, zero-knowledge payments on top of the x402 agent payment standard.

Intercepts agent transactions and checks them against 5 security oracles before execution.

Pre-built MCP blockchain capability modules giving agents fraud detection, AML scoring, wallet profiling, and token analysis.

Agent-identity authentication protocol modeled on Sign-In-With-Ethereum, letting services verify an agent before granting access.

MCP server that signs CEX/DEX orders inside an attested AWS Nitro Enclave so keys never touch the agent process.

Keyless REST APIs for token risk, approval risk, malicious addresses, signature decoding and transaction simulation across 46 chains.

Keyed risk APIs for address, contract and transaction screening, including sanction checks, across 13 documented networks.

Keyless API that simulates a buy and sell of an EVM token and reports the observed taxes, gas and honeypot result.

Public Solana token-report API: mint and freeze authority, metadata mutability, LP lockers and insider graphs, with a published OpenAPI document.

Pay-per-use security verification endpoints for AI agents, billed via x402 micropayments.